Abstract Two major tasks in spoken language understanding (SLU) are intent determination (ID) and slot filling (SF). Recurrent neural networks (RNNs) have been proved effective in SF, while there is no prior work using RNNs in ID. Based on the idea that the intent and semantic slots of a sentence are correlative, we propose a joint model for both tasks. Gated recurrent unit (GRU) is used to learn the representation of each time step, by which the label of each slot is predicted. Meanwhile, a max-pooling layer is employed to capture global features of a sentence for intent classification. The representations are shared by two tasks and the model is trained by a united loss function. We conduct experiments on two datasets, and the experimental results demonstrate that our model outperforms the state-of-theart approaches on both tasks.